MS in Data Science - Seminar Series: Machine Learning in Databases with Tyler Bettilyon
Friday, March 8 12:30 – 2 p.m.
On-Campus Event - SFH 101 Howard, Room 150
Coffee is served at the in-person seminar
Machine Learning in Databases: Learned Indexes, Hash Tables, and B-Trees
Tyler is an educator, technologist, writer, programmer, and all around curious human. He holds a bachelor’s degree in computer programming and completed his MBA by counter example in San Francisco’s startup scene. Looking out from inside the Bay Area Bubble he realized that the world is not prepared for the future that technology is bringing. He is now focused on technology education, outreach, and policy.
Indexing has a long and storied history in the world of computer science. Old stalwarts like the B-Tree and the hash table have dominated modern databases since time immemorial (the 1970's), but new research into applying ML techniques to indexing could shake up the indexing scene. While no one thinks we should throw out the beloved classics, MIT and Google researchers have made compelling case that "learned indexes" could improve storage requirements at competitive speeds. Come to this talk learn the fundamentals of indexing, and explore the trade-offs between these new "learned indexes" and the established index structures that currently dominate the field.